{"id":"W3042470307","doi":"10.48550/arxiv.2007.06731","title":"Regularized linear autoencoders recover the principal components, eventually","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regularization (linguistics); Simple (philosophy); Feature learning; Representation (politics); Principal component analysis; Computer science; Gradient descent; Mathematics; Dimension (graph theory); Artificial neural network; Convergence (economics); Mathematical optimization; Applied mathematics; Artificial intelligence; Algorithm; Combinatorics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001490883,0.001237577,0.0006266088,0.0006690402,0.0003750768,0.00116216,0.001097643,0.0009919921,0.003284147],"category_scores_gemma":[0.007201922,0.0007885206,0.0007360061,0.0007906363,0.001338462,0.002865488,0.001536061,0.002878586,0.001992394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006897476,"about_ca_system_score_gemma":0.001057307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002323949,"about_ca_topic_score_gemma":0.003721212,"domain_scores_codex":[0.999342,0.0002056658,0.00003400874,0.0002043496,0.0001597041,0.00005418926],"domain_scores_gemma":[0.9985286,0.0005567145,0.0001427396,0.0004811218,0.0002510108,0.00003977421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001278459,0.00006406787,0.001874397,0.0002100047,0.0001841265,0.0001024448,0.0001693421,0.4729254,0.00972607,0.2718205,0.009972312,0.2328237],"study_design_scores_gemma":[0.000006895359,0.00002034156,0.000455291,0.00002169014,0.00001374166,0.00003372803,0.00001612966,0.8703582,0.003006581,0.1212188,0.004836794,0.00001180262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007285851,0.0002974391,0.9894636,0.0003232084,0.00005994637,0.00001687148,0.0001409043,0.0005084554,0.001903738],"genre_scores_gemma":[0.4001454,0.001045814,0.576739,0.0004165807,0.0002165116,0.00014631,0.0008571493,0.0005350059,0.01989834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003284147,"threshold_uncertainty_score":0.01098663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1089098758402249,"score_gpt":0.2025313578770978,"score_spread":0.09362148203687297,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}